Method and equipment for judging temporary support arrangement of steel bar truss plate

Abstract

The invention provides a method and equipment for discriminating the arrangement of a temporary support for a steel bar truss plate, and the method comprises the steps: collecting a large number of steel bar truss floor support plate support layout diagrams through a training information collection and processing module, taking the layout diagrams as a training set, inputting the training set into a model training module for training, obtaining a floor support plate information recognition model, and carrying out the recognition through the model. The floor support plate information can be output to the floor support plate support intelligent distinguishing and marking module through the arrangement diagram of the steel bar truss floor support plate, and the module rapidly marks the floor support plate needing to be provided with a temporary support. According to the method, the steel bar truss floor support plate needing to be provided with the temporary support can be automatically and rapidly identified, the accuracy is high, and the efficiency is high.

Description

Technical Field

[0001] The invention relates to a method and equipment for distinguishing temporary supports for steel bar truss plates. Background Art

[0002] Steel truss floor deck is a common building structure, which is a prefabricated component composed of steel trusses and floor decks. During construction and use, when the span of some boards exceeds the support-free design span of the steel truss floor deck, supports should be set to ensure the stability of the steel truss floor deck during construction and prevent the structure from being deformed or damaged before reaching the design strength. In the past, judging whether the steel truss floor deck needs support often requires technicians to check in the drawings, which is easy to cause omissions and cause safety hazards. Summary of the invention

[0003] The purpose of the present invention is to provide a method and device for determining temporary supports for steel bar truss plates.

[0004] In order to solve the above problems, the present invention provides a method for determining whether a steel bar truss plate is provided with temporary support, comprising:

[0005] The training information acquisition and processing module collects sample floor deck layout images containing various steel trusses and obtains image information;

[0006] A training information collection and processing module is used to mark the floor deck layout image based on the image information to obtain the marked information;

[0007] Based on the image information and the annotated information, an artificial intelligence method is used to establish a floor decking information recognition model;

[0008] Input the floor deck layout image to be identified into the floor deck information recognition model to obtain the number, model, actual span value and support-free design standard span value of each floor deck;

[0009] The intelligent identification and marking module for floor deck supports determines whether each floor deck needs support based on the actual span value of each floor deck and the standard span value of the support-free design.

[0010] Furthermore, in the above method, the image information includes: span information of each floor deck, floor deck block information, actual span value of each floor deck, model of each floor deck, and standard span value of the support-free design of the floor deck corresponding to each model.

[0011] Furthermore, in the above method, the marked information includes: the marked span value of each floor decking, the edge line of each floor decking, the number of each floor decking and the model of each floor decking; wherein the actual span value of each floor decking = magnification * the marked span value of each floor decking.

[0012] Furthermore, in the above method, the information annotated in the floor decking layout image to be identified includes: the annotated span value of each floor decking, the edge line of each floor decking, the number of each floor decking and the model of each floor decking.

[0013] Furthermore, in the above method, the floor deck support intelligent identification and marking module determines whether each floor deck needs to be supported based on the actual span value of each floor deck and the standard span value of the support-free design, including:

[0014] The intelligent identification and marking module for floor deck support reads the actual span value L of each floor deck and the standard span value S of the support-free design.

[0015] When L>S, the floor deck support intelligent identification and marking module is numbered as LCB1~LCB n Mark the corresponding floor decking plate in red to indicate the location where support needs to be set.

[0016] Furthermore, in the above method, after the floor deck support intelligent identification and marking module reads the actual span value L of each floor deck and the standard span value S of the support-free design, it also includes:

[0017] When L≤S, the floor deck support intelligent identification and marking module is numbered as LCB1~LCB n， The corresponding floor decking plates are marked green to indicate locations where support is not required.

[0018] Furthermore, in the above method, after determining whether each floor deck needs to be supported, the method further includes:

[0019] After all floor decks are marked in red or green, the floor deck support intelligent identification and marking module outputs a marking diagram of the required support positions for the steel truss floor deck based on all the red marks.

[0020] Furthermore, in the above method, the floor decking information recognition model includes: CNN, RNN or ResNet models.

[0021] According to another aspect of the present invention, there is further provided a computer-readable storage medium having computer-executable instructions stored thereon, wherein when the computer-executable instructions are executed by a processor, the processor is caused to: execute any of the methods described above.

[0022] According to another aspect of the present invention, there is also provided a computer device, comprising:

[0023] Processor; and

[0024] A memory arranged to store computer executable instructions, which when executed cause the processor to: perform any of the methods described above.

[0025] Compared with the prior art, in order to solve the problem that manual verification of whether a steel truss floor deck needs temporary support is prone to errors and time-consuming, the present invention proposes a new intelligent steel truss slab temporary support identification method. Its main technical components are: a large number of steel truss floor deck support layout diagrams are collected through the training information collection and processing module, used as training sets, and the training sets are input into the model training module for training to obtain a floor deck information recognition model. Using this model, the floor deck information can be output to the floor deck support intelligent identification and marking module through the steel truss floor deck layout diagram, and the module quickly marks the floor deck that needs to be temporarily supported. This method can realize automatic and rapid identification of steel truss floor decks that need to be temporarily supported, with high accuracy and efficiency.

[0026] Compared with the current temporary support arrangement method for floor decking, the beneficial effects of the present invention are mainly as follows:

[0027] (1) High accuracy. The intelligent steel truss plate temporary support identification method of the present invention can avoid omissions and has high accuracy compared with the manual arrangement method;

[0028] (2) High efficiency. Compared with the manual layout method, this method can quickly find and mark all floor decking slabs whose spans exceed the design requirements. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] Figure 1 It is a schematic diagram of a method and device for determining temporary support for a steel truss plate according to an embodiment of the present invention;

[0030] Figure 2 is a schematic diagram of a floor deck arrangement image to be identified according to an embodiment of the present invention;

[0031] Figure 3 It is a marking diagram of the support positions where the output steel bar truss floor decking needs to be set according to an embodiment of the present invention. DETAILED DESCRIPTION

[0032] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the present invention is further described in detail below with reference to the accompanying drawings and specific embodiments.

[0033] like Figure 1 As shown, the present invention provides a method and device for determining temporary support for a steel truss plate, comprising:

[0034] Step S1, training the information collection and processing module, collecting sample floor deck layout images containing various steel trusses, and obtaining image information;

[0035] Preferably, the image information includes: span information of each floor deck, floor deck block information, actual span value of each floor deck, model of each floor deck, and standard span value of the support-free design of the floor deck corresponding to each model;

[0036] Here, the floor decking block information includes: the edge line of each floor decking block;

[0037] like Figure 2 As shown, each floor decking plate LCB1~LCB n Set between the beams 1 and columns 2 of the building, the boundaries of each floor slab are distinguished by their respective edge lines 3;

[0038] Step S2, training information collection and processing module, based on the image information, marking on the floor deck layout image to obtain marked information;

[0039] Preferably, the marked information includes: the marked span value of each floor deck, the edge line of each floor deck, the number of each floor deck and the model of each floor deck; wherein the actual span value of each floor deck = magnification * the marked span value of each floor deck; for example, Figure 2 As shown, the span of each floor deck is marked as a, the length is b, and the magnification is 8000 / b. The span L1 of the floor deck LCB1 in the figure is L1 = 8000 × a / b, in mm.

[0040] The OCR technology can be used to extract the text of the span information of each floor deck in the image information, and then mark the span value of each floor deck;

[0041] In the process of marking based on the floor decking block information, all floor decking can be divided according to the edge line of each floor decking, and each floor decking is numbered from left to right and from top to bottom starting from the upper left corner of the sample floor decking layout image. The number names are LCB1~LCB n ;

[0042] The marked floor deck model includes: floor deck model name, for example, there are m models, models are XH1~XH m :

[0043] Through the span marking value and magnification of each floor decking plate, the actual span value corresponding to the number of each floor decking plate is calculated and recorded as L1~L n ;

[0044] The support-free design span value corresponding to each type of floor deck is recorded as S1~S m ;

[0045] Step S3, based on the image information and the annotated information, using an artificial intelligence method, establishing a floor deck information recognition model;

[0046] Preferably, the form of the floor deck information recognition model is not limited, and models such as CNN, RNN and ResNet can be used to establish a multi-span beam structure information recognition model;

[0047] To ensure the training effect, the training set needs more than 1,000 sets of data;

[0048] The model training process can use algorithms such as stochastic gradient descent and adaptive gradient algorithm to train the model until the loss function is less than the preset value, and then the training ends;

[0049] like Figure 2 As shown, step S4, inputting the floor deck layout image to be identified into the floor deck information recognition model to obtain the number, model, actual span value L and support-free design standard span value S of each floor deck;

[0050] Preferably, the information annotated in the floor deck layout image to be identified includes: the annotated span value of each floor deck, the edge line of each floor deck, the number of each floor deck and the model of each floor deck;

[0051] Here, the model input may be: a marked floor deck layout drawing, including: the span marking value of each floor deck, the edge line of each floor deck, the number of each floor deck, and the type of each floor deck;

[0052] The model output can be: span information of each floor decking, board division information, actual span value of each floor decking, model of each floor decking, support-free design span information of the floor decking. The number, model, actual span value L of the floor decking and standard span value S of the support-free design of the floor decking of the same floor decking can be integrated into the same set of data to facilitate the intelligent identification and marking module processing of the floor decking support.

[0053] Step S5, the floor deck support intelligent identification and marking module determines whether each floor deck needs to be supported based on the actual span value L of each floor deck and the support-free design standard span value S.

[0054] Preferably, the floor deck support intelligent identification and marking module can read the actual span value L of each floor deck and the standard span value S of the support-free design. When L>S, the floor deck support intelligent identification and marking module, according to the number LCB1~LCB n The corresponding floor deck is marked in red to indicate the location where support needs to be set; when L≤S, the floor deck support intelligent identification and marking module is numbered LCB1~LCBn， The corresponding floor decking plates are marked green to indicate the locations where no support is required;

[0055] More preferably, after all floor decks are marked with red or green, the floor deck support intelligent identification and marking module outputs a marking diagram of the steel truss floor deck that needs to set the support position 4 based on all red marks, such as Figure 3 shown.

[0056] According to another aspect of the present invention, there is further provided a computer-readable storage medium having computer-executable instructions stored thereon, wherein when the computer-executable instructions are executed by a processor, the processor is caused to: execute any of the methods described above.

[0057] According to another aspect of the present invention, there is also provided a computer device, comprising:

[0058] Processor; and

[0059] A memory arranged to store computer executable instructions, which when executed cause the processor to: perform any of the methods described above.

[0060] In summary, in order to solve the problem that manual verification of whether a steel truss floor deck needs temporary support is prone to errors and time-consuming, the present invention proposes a new intelligent steel truss slab temporary support identification method. Its main technical components are: a large number of steel truss floor deck support layout diagrams are collected through the training information acquisition and processing module, used as training sets, and the training sets are input into the model training module for training to obtain a floor deck information recognition model. Using this model, the floor deck information can be output to the floor deck support intelligent identification and marking module through the steel truss floor deck layout diagram, and the module will quickly mark the floor deck that needs temporary support. This method can realize the automatic and rapid identification of steel truss floor decks that need temporary support, with high accuracy and efficiency.

[0061] Compared with the current temporary support arrangement method for floor decking, the beneficial effects of the present invention are mainly as follows:

[0062] (1) High accuracy. The intelligent steel truss plate temporary support identification method of the present invention can avoid omissions and has high accuracy compared with the manual arrangement method;

[0063] (2) High efficiency. Compared with the manual layout method, this method can quickly find and mark all floor decking slabs whose spans exceed the design requirements.

[0064] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the various embodiments can be referenced to each other.

[0065] Professionals may further appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in the above description according to function. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians may use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0066] Obviously, those skilled in the art can make various changes and modifications to the invention without departing from the spirit and scope of the invention. Thus, if these modifications and variations of the invention fall within the scope of the claims of the invention and their equivalents, the invention is also intended to include these modifications and variations.

Claims

1. A method for determining temporary support for a steel truss plate, characterized in that: include: The training information acquisition and processing module collects sample floor deck layout images containing various steel trusses and obtains image information; A training information collection and processing module is used to mark the floor deck layout image based on the image information to obtain the marked information; Based on the image information and the annotated information, an artificial intelligence method is used to establish a floor decking information recognition model; Input the floor deck layout image to be identified into the floor deck information recognition model to obtain the number, model, actual span value and support-free design standard span value of each floor deck; The intelligent identification and marking module for floor deck supports determines whether each floor deck needs support based on the actual span value of each floor deck and the standard span value of the support-free design.

2. The method for determining whether a steel bar truss plate is provided with temporary support according to claim 1, characterized in that: The image information includes: span information of each floor deck, floor deck block information, actual span value of each floor deck, model of each floor deck, and standard span value of the support-free design of the floor deck corresponding to each model.

3. The method for determining whether a steel bar truss plate is provided with temporary support according to claim 2, characterized in that: The marked information includes: the marked span value of each floor decking, the edge line of each floor decking, the serial number of each floor decking and the model of each floor decking; wherein the actual span value of each floor decking = magnification * the marked span value of each floor decking.

4. The method for determining whether a steel bar truss plate is provided with temporary support according to claim 3, characterized in that: The information marked in the floor deck layout image to be identified includes: the marked span value of each floor deck, the edge line of each floor deck, the number of each floor deck and the model of each floor deck.

5. The method for determining whether a steel bar truss plate is provided with temporary support according to claim 1, characterized in that: The intelligent identification and marking module for floor deck support determines whether each floor deck needs support based on the actual span value of each floor deck and the standard span value of the support-free design, including: The intelligent identification and marking module for floor deck support reads the actual span value L of each floor deck and the standard span value S of the support-free design. When L>S, the floor deck support intelligent identification and marking module is numbered as LCB1~LCB n Mark the corresponding floor decking plate in red to indicate the location where support needs to be set.

6. The method for determining whether a steel bar truss plate is provided with temporary support according to claim 5, characterized in that: The intelligent identification and marking module for floor deck support reads the actual span value L of each floor deck and the standard span value S of the support-free design, and also includes: When L≤S, the floor deck support intelligent identification and marking module is numbered as LCB1~LCB n， The corresponding floor decking plates are marked green to indicate locations where support is not required.

7. The method for determining whether a steel bar truss plate is provided with temporary support according to claim 5, characterized in that: After determining whether each floor deck needs support, it also includes: After all floor decks are marked in red or green, the floor deck support intelligent identification and marking module outputs a marking diagram of the required support positions for the steel truss floor deck based on all the red marks.

8. The method for determining whether a steel bar truss plate is provided with temporary support according to claim 1, characterized in that: Floor deck information recognition model, including: CNN, RNN or ResNet model.

9. A computer-readable storage medium having computer-executable instructions stored thereon, wherein: When the computer executable instructions are executed by a processor, the processor is caused to: perform the method according to any one of claims 1 to 8.

10. A computer device, wherein: include: processor; as well as A memory arranged to store computer executable instructions which, when executed, cause the processor to: perform a method as claimed in any one of claims 1 to 8.

Images